Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5219
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Locations or place names

    np_acts-logits-general · gemini-2.0-flash

    Times Square and central squares

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.66
    
    -0.63
    Midwest
    -0.56
    tagHelperRunner
    -0.54
    ńst
    -0.53
    rshire
    -0.52
    DIPSETTING
    -0.52
    enumii
    -0.51
    脚注の使い方
    -0.50
     Midwest
    -0.50
    POSITIVE LOGITS
     square
    1.10
     Square
    1.07
     street
    1.03
     SQUARE
    0.93
     squares
    0.93
     piazza
    0.92
    Square
    0.90
     Piazza
    0.88
    square
    0.86
     plaza
    0.84
    Activations Density 0.238%

    No Known Activations